Update README.md

README.md

@@ -13,7 +13,7 @@ license_link: https://ai.google.dev/gemma/terms
 
 **Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
 
-This model card corresponds to the 7B base version of the Gemma model. You can also visit the model card of the [2B base model](https://huggingface.co/google/gemma-2b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it). 
+This model card corresponds to the 2B base version of the Gemma model. You can also visit the model card of the [7B base model](https://huggingface.co/google/gemma-7b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it). 
 
 **Resources and Technical Documentation**:
 
@@ -59,8 +59,8 @@ You can find fine-tuning notebooks under the [`examples/` directory](https://hug
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt")
@@ -69,6 +69,23 @@ outputs = model.generate(**input_ids)
 print(tokenizer.decode(outputs[0]))
 ```
 
+#### Running the model using Flax on a single GPU / TPU 
+
+
+```python
+from transformers import AutoTokenizer, FlaxGemmaForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = FlaxGemmaForCausalLM.from_pretrained("google/gemma-2b-flax")
+model.params = jax.tree_map(lambda x: jax.device_put(x, jax.devices()[0]).astype(jnp.float16), flax.params)
+
+input_text = "Write me a poem about Machine Learning."
+input_ids = jax.device_put(tokenizer(input_text, return_tensors="jax"), jax.devices()[0])
+
+outputs = model.generate(**input_ids)
+print(tokenizer.decode(outputs[0][0]))
+```
+
 
 #### Running the model on a single / multi GPU
 
@@ -77,8 +94,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto")
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -96,8 +113,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto", torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.float16)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -112,8 +129,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto", torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.bfloat16)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -132,8 +149,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config=quantization_config)
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -150,8 +167,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(load_in_4bit=True)
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config=quantization_config)
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")